AI RESEARCH
Adaptive Voxel-Weighted Loss Using L1 Norms in Deep Neural Networks for Detection and Segmentation of Prostate Cancer Lesions in PET/CT Images
arXiv CS.AI
•
ArXi:2502.02756v2 Announce Type: replace-cross Accurate automated detection of recurrent prostate cancer in PSMA PET/CT scans is challenging due to heterogeneous lesion size, activity, anatomical location, and intra- and inter-class imbalances. Conventional deep learning loss functions often produce suboptimal optimization, as gradients are dominated by easy background voxels or extreme outliers.